Summary
AWS cares about Developers. The event begins with the Developer Experience (DevEx) Section. The speaker, Teddy, described why DX is important and how to measure it.
DevEx can be quantified with 3 aspects: Feedback loops/ Cognitive load/ Flow stare
For developers, we always care about productivity and satisfaction. To get that, it’s all about how to get into the “zone”. The key idea that Teddy proposed is to pay attention to who/what broke our “zone” and try to avoid that.
Another post: https://github.blog/2023-06-08-developer-experience-what-is-it-and-why-should-you-care/
Generative AI plays a big role in every industry. In this event, AWS shows how powerful it is and introduces Retrieval Augmented Generation (RAG) from Meta. RAG combines an information retrieval component with a text generator model. RAG shows a good way to integrate the LLM model with your private data.
RAG architecture
To be able to use RAG, several key components are covered in the conference,
- How to store data: vector database
- Where to run the model: new EC2 instance: P5
- DevOps
Vector Database
Vector databases provide the ability to store and retrieve vectors as high-dimensional points. They add additional capabilities for efficient and fast lookup of nearest-neighbors in the N-dimensional space. They are typically powered by k-nearest neighbor (k-NN) indexes and built with algorithms like the Hierarchical Navigable Small World (HNSW) and Inverted File Index (IVF) algorithms. Vector databases provide additional capabilities like data management, fault tolerance, authentication and access control, and a query engine.
from: https://aws.amazon.com/what-is/vector-databases/
recommend reading: The role of vector datastores in generative AI applications
DevOps: Best Practice
Key: make sure the local environment is the same among developers. Normally it’s where the issue comes from.
Joined Section
- Opening Keynote — Improving Developer Experience on AWS — an in-depth look at industry best practices (English session)
- Transforming Digital Experiences with Generative AI: Video Search and Content Moderation
- Co-innovate with NVIDIA: Generative AI Software Ecosystem
- 出版產業 stable diffusion 的應用
- 運用 Amazon 向量資料庫促進 Generative AI 創新應用 (Track 1)
- 從開發者眼中看到的 Well-Architected Best Practices (Track 2)
- 利用 AWS 雲服務，構建端到端的 Generative AI 應用 (Track 3)
